Support Vector Machine with Particle Swarm Optimization for Reservoir Annual Inflow Forecasting

Reservoir inflow forecasting plays an essential role in reservoir management to ensure efficient water supply and more high accuracy inflow forecasting can lead to more effective use of water resources. In this study, support vector machine (SVM) with particle swarm optimization (PSO) for reservoir annual inflow forecasting is presented, among which PSO is used to find out the best parameter value of SVM model. According to study data, the optimum SVM model is obtained and its performance is compared with Artificial Neural Networks (ANNs). It can be concluded that the performance of SVM model outperforms those of ANN, for the data set available, which indicates that the SVM model has better forecasting performance.